{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XI7SRVA3MZW7K6DL4IHNU3V45L","short_pith_number":"pith:XI7SRVA3","canonical_record":{"source":{"id":"2309.04814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-09T14:52:39Z","cross_cats_sorted":[],"title_canon_sha256":"acf84bb86387b5b3372e05002f7ba18a875f9500d16e4f107b0456878ddb802f","abstract_canon_sha256":"d52580055a22dfab103b8a5a87afa7e4b3871b821ddf72139e2d3f13b0115d9c"},"schema_version":"1.0"},"canonical_sha256":"ba3f28d41b666df5786be20eda6ebceaf2affaf747e25a3fc7040d4424f0c6b9","source":{"kind":"arxiv","id":"2309.04814","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04814","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04814v1","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04814","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"XI7SRVA3MZW7","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"pith_short_16","alias_value":"XI7SRVA3MZW7K6DL","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"pith_short_8","alias_value":"XI7SRVA3","created_at":"2026-07-05T06:49:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XI7SRVA3MZW7K6DL4IHNU3V45L","target":"record","payload":{"canonical_record":{"source":{"id":"2309.04814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-09T14:52:39Z","cross_cats_sorted":[],"title_canon_sha256":"acf84bb86387b5b3372e05002f7ba18a875f9500d16e4f107b0456878ddb802f","abstract_canon_sha256":"d52580055a22dfab103b8a5a87afa7e4b3871b821ddf72139e2d3f13b0115d9c"},"schema_version":"1.0"},"canonical_sha256":"ba3f28d41b666df5786be20eda6ebceaf2affaf747e25a3fc7040d4424f0c6b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:27.576906Z","signature_b64":"z1Da5IVRtbjZYsydaXZokGQeH7b6KpgpUZEGlRVuHzCT4AGY879k/UPilTMFd5I8JTUIVebTt9Ut7PzvzhdRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba3f28d41b666df5786be20eda6ebceaf2affaf747e25a3fc7040d4424f0c6b9","last_reissued_at":"2026-07-05T06:49:27.576483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:27.576483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.04814","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9+SCeOdGe+6dheEOx45FRuHhlxqbgZV1JQbKvYg3rW6GJvEB2JkA0Hi4SpC0/VeW6+8hEtYBp/k0v1bGe4EYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:27:28.406531Z"},"content_sha256":"7a55741cc81635da46a86cba87699e768a20929410b475b46d8cb2a2f169cdf0","schema_version":"1.0","event_id":"sha256:7a55741cc81635da46a86cba87699e768a20929410b475b46d8cb2a2f169cdf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XI7SRVA3MZW7K6DL4IHNU3V45L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pengfei Hu, Wenming Yang, Xiaojuan Qi, Xiaoyang Lyu, Xiuzhe Wu, Yang Wu, Yan-Pei Cao, Ying Shan, Zhongqian Sun","submitted_at":"2023-09-09T14:52:39Z","abstract_excerpt":"Synthesizing realistic videos according to a given speech is still an open challenge. Previous works have been plagued by issues such as inaccurate lip shape generation and poor image quality. The key reason is that only motions and appearances on limited facial areas (e.g., lip area) are mainly driven by the input speech. Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training. We thus propose a decomposition-synthesis-composition framework named Speech to Lip (Speech2Lip) that disentangles "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04814","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.04814/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ox0ovi98SGUSy51PHVrsPDWfBFWa0CZxxh35/6xk/v2GNNANXOP+WBLajbr43qSCWgJmOgIA8kE6FBYrhLmODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:27:28.407495Z"},"content_sha256":"9a732c6f11694543316c94182b7d5f23b4d8b1d656586f4e52e1899e9e0cefe1","schema_version":"1.0","event_id":"sha256:9a732c6f11694543316c94182b7d5f23b4d8b1d656586f4e52e1899e9e0cefe1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XI7SRVA3MZW7K6DL4IHNU3V45L/bundle.json","state_url":"https://pith.science/pith/XI7SRVA3MZW7K6DL4IHNU3V45L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XI7SRVA3MZW7K6DL4IHNU3V45L/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T08:27:28Z","links":{"resolver":"https://pith.science/pith/XI7SRVA3MZW7K6DL4IHNU3V45L","bundle":"https://pith.science/pith/XI7SRVA3MZW7K6DL4IHNU3V45L/bundle.json","state":"https://pith.science/pith/XI7SRVA3MZW7K6DL4IHNU3V45L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XI7SRVA3MZW7K6DL4IHNU3V45L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XI7SRVA3MZW7K6DL4IHNU3V45L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d52580055a22dfab103b8a5a87afa7e4b3871b821ddf72139e2d3f13b0115d9c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-09T14:52:39Z","title_canon_sha256":"acf84bb86387b5b3372e05002f7ba18a875f9500d16e4f107b0456878ddb802f"},"schema_version":"1.0","source":{"id":"2309.04814","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04814","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04814v1","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04814","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"XI7SRVA3MZW7","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"pith_short_16","alias_value":"XI7SRVA3MZW7K6DL","created_at":"2026-07-05T06:49:27Z"},{"alias_kind":"pith_short_8","alias_value":"XI7SRVA3","created_at":"2026-07-05T06:49:27Z"}],"graph_snapshots":[{"event_id":"sha256:9a732c6f11694543316c94182b7d5f23b4d8b1d656586f4e52e1899e9e0cefe1","target":"graph","created_at":"2026-07-05T06:49:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.04814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthesizing realistic videos according to a given speech is still an open challenge. Previous works have been plagued by issues such as inaccurate lip shape generation and poor image quality. The key reason is that only motions and appearances on limited facial areas (e.g., lip area) are mainly driven by the input speech. Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training. We thus propose a decomposition-synthesis-composition framework named Speech to Lip (Speech2Lip) that disentangles ","authors_text":"Pengfei Hu, Wenming Yang, Xiaojuan Qi, Xiaoyang Lyu, Xiuzhe Wu, Yang Wu, Yan-Pei Cao, Ying Shan, Zhongqian Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-09T14:52:39Z","title":"Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04814","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7a55741cc81635da46a86cba87699e768a20929410b475b46d8cb2a2f169cdf0","target":"record","created_at":"2026-07-05T06:49:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d52580055a22dfab103b8a5a87afa7e4b3871b821ddf72139e2d3f13b0115d9c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-09T14:52:39Z","title_canon_sha256":"acf84bb86387b5b3372e05002f7ba18a875f9500d16e4f107b0456878ddb802f"},"schema_version":"1.0","source":{"id":"2309.04814","kind":"arxiv","version":1}},"canonical_sha256":"ba3f28d41b666df5786be20eda6ebceaf2affaf747e25a3fc7040d4424f0c6b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba3f28d41b666df5786be20eda6ebceaf2affaf747e25a3fc7040d4424f0c6b9","first_computed_at":"2026-07-05T06:49:27.576483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:27.576483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z1Da5IVRtbjZYsydaXZokGQeH7b6KpgpUZEGlRVuHzCT4AGY879k/UPilTMFd5I8JTUIVebTt9Ut7PzvzhdRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:27.576906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04814","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a55741cc81635da46a86cba87699e768a20929410b475b46d8cb2a2f169cdf0","sha256:9a732c6f11694543316c94182b7d5f23b4d8b1d656586f4e52e1899e9e0cefe1"],"state_sha256":"59d8cc8accc07630537a17a668c575aaab16bce422692301d4e8caba465f444a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGU5PRHnLNqqPog6bjVlnzRhx89BDJrFHFvd0vPPOEdcKjgtGNs03egbrdgdsPQq3PTuGdCUbiWObErDk7+PAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:27:28.421178Z","bundle_sha256":"f6dcdeb039fd38f2d6854e9e243c4b8a1869ce2c15de13b2d0b0670b4afb49a4"}}